A fast algorithm for background tracking in video surveillance, using nonparametric kernel density estimation

Abstract

Moving object detection and tracking in video surveillance systems is commonly based on background estimation and subtraction. For satisfactory performance in real world applications, robust estimators, tolerating the presence of outliers in the data, are needed. Nonparametric kernel density estimation has been successfully used in modeling the background statistics, due to its capability to perform well without making any assumption about the form of the underlying distributions. However, in real-time applications, the O(N 2) complexity of the method can be a bottleneck, preventing the object tracking and event analysis modules from having the computing time needed. In this paper, we propose a new background subtraction technique, using multiresolution and recursive density estimation with mean shift based mode tracking. An algorithm with complexity independent on N is developed for fast, real-time implementation. Comparative results with known methods are included, in order to attest the effectiveness and quality of the proposed approach.

N-queens-based algorithm for moving object detection in distributed wireless sensor networks

“…The next stages (object tracking and higher level processing) heavily depend on the accuracy and robustness of the first step of moving object detection [1].…”

Moving/motionless foreground object detection using fast statistical background updating

“…Rather than modelling the features of each pixel with Gaussian distributions, Elgammal et al 22 and Ianasi et al 23 evaluated the probability of a background pixel using kernel density estimation from very recent historical samples in the image sequence. Elgammal et al 24 also used Fast Gauss Transform 25 to improve the computation of the Gaussian kernel density estimation.…”

High Accuracy Detection and Tracking of Objects

“…Applications include car and pedestrian traffic monitoring, human activity surveillance for unusual activity detection, people counting etc., [3]. DETECTION of moving objects in the video streams is the first important step of information extraction in many computer vision applications, including video surveillance, people tracking, traffic monitoring and semantic annotation of videos.…”